INDEX

Explanations

many, much, other, some

The main thing this neuron does is detect words expressing quantity, degree, or comparative emphasis.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

當然

-1.66

・・・・・

-1.59

If

-1.54

はコチラ

-1.53

Descubre

-1.50

有什麼

-1.48

の詳細

-1.47

连连

-1.42

を選

-1.42

Here

-1.42

POSITIVE LOGITS

and

1.81

for

1.51

so

1.46

@[+][

1.45

高原

1.45

╔

1.41

NUC

1.38

errorCode

1.38

’?

1.35

 แต่

1.33

Activations Density 0.009%